fusion-issue-solving

Handles GitHub issue resolution end-to-end for prompts like "solve #123", "lets solve #123", "work on #123", "work on https://github.com/owner/repo/issues/123", or by pasting a direct GitHub issue URL as the request. USE FOR: solve #123, continue work on issue #123, work on https://github.com/owner/repo/issues/123, paste a GitHub issue URL for implementation work. DO NOT USE FOR: issue drafting only, PR review only, or non-implementation research.

Quality

85%

Does it follow best practices?

Run evals on this skill

Adds up to 20 points to the overall score

View guide

Securityby

Low

Low-risk findings worth noting

Quality

Content

81%Weight 40%Scale 1-5

Reviews the quality of instructions and guidance provided to agents. Good implementation is clear, handles edge cases, and produces reliable results.

A well-structured, mutation-aware workflow with strong sequencing and explicit validation checkpoints. The main improvements are tightening trigger-list duplication with the description and pushing more operational detail (rate-limit budgets, GraphQL costs) into the referenced asset.

Suggestions

Remove the duplicated trigger-phrase list in '## When to use' since the frontmatter description already enumerates them; keep only a one-line summary plus the URL-interchangeability note.

Move the detailed low-token budget figures (5 secondary-limit points per mutation, ~20 read / ~5 mutation ceilings, 30+ call pause rule) into assets/issue-solving-checklist.md and reference it, keeping SKILL.md to the MCP-first principle.

Tighten steps 6 and 7 with prescriptive guidance (e.g., which test commands to locate first) instead of 'Inspect relevant files' / 'Implement in small scoped changes' to lift actionability.

Dimension	Reasoning	Score
Conciseness	Largely efficient and assumes Claude's competence (no explainer on what GitHub/issues are), but the 'When to use' trigger list duplicates the description's triggers and the low-token strategy section carries some dense operational detail that could be trimmed into the checklist asset.	4 / 5
Actionability	Delivers concrete, directive guidance — specific file-naming patterns, MCP-first vs GraphQL fallback rules, and explicit 'ask before...' gates — though a few steps ('Inspect relevant files', 'Research before edits') remain high-level rather than prescriptive.	4 / 5
Workflow Clarity	A clearly sequenced 10-step workflow with an explicit validation feedback loop (step 8: run checks, fix, re-run before proceeding), safety constraints, and a linked checklist — satisfying the top anchor for explicit validation steps and error-recovery loops on a mutation-capable skill.	5 / 5
Progressive Disclosure	Well-organized into clearly labeled sections with a one-level-deep, verified asset reference (assets/issue-solving-checklist.md) under '## Assets'; minor gap is that the checklist largely re-states the inline steps rather than offloading distinct detail.	4 / 5
	Total	17 / 20 Passed

Description

90%Weight 40%Scale 1-5

Based on the skill's description, can an agent find and select it at the right time? Clear, specific descriptions lead to better discovery.

A strong, trigger-rich description that clearly states capability, when to use it, and when not to. Its only weakness is that the 'what' centers on a single end-to-end workflow rather than enumerating several distinct concrete actions.

Dimension	Reasoning	Score
Specificity	Names the domain and a couple of concrete actions ('issue resolution end-to-end', 'continue work', 'implementation work') but these are variations of one workflow rather than a comprehensive list of distinct capabilities, matching the 'names domain and 1-2 concrete actions' anchor.	3 / 5
Completeness	Explicitly answers both 'what' ('Handles GitHub issue resolution end-to-end') and 'when' ('USE FOR:' with concrete trigger phrases), plus a 'DO NOT USE FOR' boundary — matching the top anchor for explicit what-and-when with concrete triggers.	5 / 5
Trigger Term Quality	Comprehensive coverage of natural trigger phrasings users would actually say — 'solve #123', 'lets solve #123', 'work on #123', 'continue work on issue #123', and full GitHub issue URL forms — including synonyms and URL-format variations.	5 / 5
Distinctiveness Conflict Risk	Clear niche (end-to-end implementation issue resolution) with distinct triggers and an explicit 'DO NOT USE FOR: issue drafting only, PR review only' boundary that minimizes overlap with adjacent issue/PR skills.	5 / 5
	Total	18 / 20 Passed

Validation

93%

Warnings & errors only

Checks the skill against the spec for correct structure and formatting. All validation checks must pass before discovery and implementation can be scored.

Validation — 15 / 16 Passed

Validation for skill structure

Criteria	Description	Result
metadata_field	'metadata' should map string keys to string values	Warning

	Total	15 / 16 Passed

Repository: equinor/fusion-framework
Path: .agents/skills/fusion-issue-solving/SKILL.md
Commit: 5b70066

Reviewed: 2 days ago

Table of Contents

Discovery Implementation Validation

Is this your skill?

If you maintain this skill, you can claim it as your own. Once claimed, you can manage eval scenarios, bundle related skills, attach documentation or rules, and ensure cross-agent compatibility.